US20070150654A1 - Storage apparatus using non-volatile memory as cache and method of managing the same - Google Patents
Storage apparatus using non-volatile memory as cache and method of managing the same Download PDFInfo
- Publication number
- US20070150654A1 US20070150654A1 US11/601,819 US60181906A US2007150654A1 US 20070150654 A1 US20070150654 A1 US 20070150654A1 US 60181906 A US60181906 A US 60181906A US 2007150654 A1 US2007150654 A1 US 2007150654A1
- Authority
- US
- United States
- Prior art keywords
- block
- allocated
- physical
- list
- storage apparatus
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
- G06F12/0802—Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
- G06F12/0866—Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches for peripheral storage systems, e.g. disk cache
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F12/00—Accessing, addressing or allocating within memory systems or architectures
- G06F12/02—Addressing or allocation; Relocation
- G06F12/0223—User address space allocation, e.g. contiguous or non contiguous base addressing
- G06F12/023—Free address space management
- G06F12/0238—Memory management in non-volatile memory, e.g. resistive RAM or ferroelectric memory
- G06F12/0246—Memory management in non-volatile memory, e.g. resistive RAM or ferroelectric memory in block erasable memory, e.g. flash memory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/10—Providing a specific technical effect
- G06F2212/1032—Reliability improvement, data loss prevention, degraded operation etc
- G06F2212/1036—Life time enhancement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/22—Employing cache memory using specific memory technology
- G06F2212/222—Non-volatile memory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/28—Using a specific disk cache architecture
- G06F2212/282—Partitioned cache
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2212/00—Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
- G06F2212/72—Details relating to flash memory management
- G06F2212/7211—Wear leveling
Definitions
- aspects of the present invention relate to storage apparatuses using a non-volatile memory as a cache and methods of managing the same. More particularly, aspects of the present invention relate to storage apparatuses using non-volatile memory, which retains data even after power interruption, as a cache and methods of managing the same.
- a conventional storage apparatus 10 includes a host 11 , a data buffer 12 , and a main storage medium 13 .
- the host 11 transmits/receives data to/from the main storage medium 13 in accordance with a user's command.
- the data buffer 12 buffers the difference in rate between the host 11 and the main storage medium 13 .
- the data buffer 12 of the storage apparatus 10 is generally composed of a volatile memory. This means that, when power supply to the main storage device 10 is interrupted, all data existing in the data buffer 12 is lost.
- the storage apparatus 10 uses a cache, which stores a part of the data that is to be stored in the main storage medium 13 .
- a cache which stores a part of the data that is to be stored in the main storage medium 13 .
- the data buffer 12 cannot be used as a cache, even when the size of the data buffer 12 is increased, because it loses all data when the power supply is interrupted.
- the fact that the main storage medium 13 must be always supplied with power is an obstacle to reducing power consumption.
- a non-volatile memory as the cache of the storage apparatus 10 so that, when the host 11 reads/writes data from/to the non-volatile memory, power supply to the main storage medium 13 is interrupted so as to reduce the power consumption.
- non-volatile memory as the cache of the storage apparatus 10 has the following problems: data must be efficiently managed according to whether or not it is fixed.
- the non-volatile memory has a fixed region, in which data is fixedly positioned all the time, and a non-fixed region in which position of data is changed frequently. These regions must be managed efficiently.
- a method of protecting data against unexpected power interruption is necessary.
- There is also a need to provide a method of collecting blocks in order to minimize the time of power supply to the main storage medium 13 as well as a method of increasing the life of the non-volatile memory in consideration of the wear level of respective physical blocks in the non-volatile memory.
- Laid-open Japanese Patent No. 2003-256289 discloses a system for maintaining the consistency of wear level of a flash memory system, the address of which can be designated as desired, by periodically deleting the designation of blocks, which have been grouped in the flash memory, according to a circular sequence (recording and deletion occur at both the bottom and top of a physical sector address).
- the system disclosed in Japanese Patent No. 2003-256289 does not propose a method of efficiently managing data in fixed and non-fixed regions, nor does it suggest protecting data against unexpected power interruption, or increasing lifespan based on block collection and wear level adjustment.
- An aspect of the present invention provides a storage apparatus using a non-volatile memory as its cache in such a manner that the non-volatile memory is separately managed by dividing it into fixed and non-fixed regions in accordance with whether or not data is fixed in the regions and blocks are collected for uniform wear level of the blocks, as well as a method of managing the same.
- Another aspect of the present invention provides a storage apparatus using a non-volatile memory as its cache for easy recovery from unexpected power interruption and a method for managing the same.
- a storage apparatus using a non-volatile memory as a cache including a main storage medium; a non-volatile memory used as a cache of the main storage medium, a region of the non-volatile memory being divided into a fixed region and a non-fixed region according to whether or not data is fixed; and a block management unit managing physical blocks by means of virtual addresses, the physical blocks being allocated to the non-volatile memory.
- a method of managing a storage apparatus using a non-volatile memory as a cache including dividing a region of a non-volatile memory used as a cache of a main storage medium into a fixed region and a non-fixed region according to whether or not data is fixed and managing physical blocks allocated to the fixed region and the non-fixed region by means of virtual addresses allocated to the physical blocks, respectively.
- FIG. 1 shows a conventional storage apparatus
- FIG. 2 shows a storage apparatus using a non-volatile memory as its cache according to an exemplary embodiment of the present invention
- FIG. 3 shows a virtual block address space according to an exemplary embodiment of the present invention
- FIG. 4 shows an allocated block list and a free block list according to an exemplary embodiment of the present invention
- FIG. 5 shows a block mapping table according to an exemplary embodiment of the present invention
- FIG. 6 shows an allocated block list, a free block list, and a block mapping table, before blocks are collected, according to an exemplary embodiment of the present invention
- FIG. 7 shows an allocated block list, a free block list, and a block mapping table, after blocks are collected, according to an exemplary embodiment of the present invention
- FIG. 8 shows an allocated block list, a free block list, and a block mapping table, before a bad block is processed, according to an exemplary embodiment of the present invention
- FIG. 9 shows an allocated block list, a free block list, and a block mapping table, after a bad block is processed, according to an exemplary embodiment of the present invention
- FIG. 10 shows a method of allocating blocks according to an exemplary embodiment of the present invention
- FIG. 11 shows a method of collecting blocks according to an exemplary embodiment of the present invention
- FIG. 12 shows a method of processing a bad block according to an exemplary embodiment of the present invention.
- FIG. 13 shows a method of recovering from power interruption according to an exemplary embodiment of the present invention.
- These computer program instructions may also be stored in a computer usable or computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer usable or computer-readable memory produce an article of manufacture including instruction means that implement the functions specified in the flowchart block or blocks.
- the computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.
- each block of the flowchart illustrations may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks may occur out of the order shown. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
- FIG. 2 shows a storage apparatus using a non-volatile memory as its cache according to an exemplary embodiment of the present invention.
- a storage apparatus 100 using a non-volatile memory as its cache may include a main storage medium 110 , a non-volatile memory 120 used as the cache of the main storage medium 110 , and a block management unit 130 for managing the Physical Block (PB) of the non-volatile memory 120 by means of virtual addresses.
- PB Physical Block
- the main storage medium 110 is a large-capacity storage medium, such as a hard disk drive
- the non-volatile memory 120 is, for example, a flash memory capable of retaining data even in the case of power interruption.
- the storage apparatus 100 using a non-volatile memory as its cache according to the present exemplary embodiment may be connected to a host 140 , which transmits/receives data to/from the main storage medium 110 in accordance with the user's command.
- the host 140 may be connected to the block management unit 130 .
- the non-volatile memory 120 may be divided into a fixed region in which data is fixed and a non-volatile region in which data is changed frequently.
- the fixed region stores data that is supposed to permanently reside in the non-volatile memory 120 and is used as the cache of the main storage apparatus 110 .
- data frequently moves to/from the main storage medium 110 .
- the block management unit 130 may include a block allocation unit 131 for allocating PBs to the non-volatile memory 120 ; a block collection unit 132 for collecting allocated PBs; a bad block management unit 133 for managing bad blocks; a power interruption recovery unit 134 for recovering from power interruption; a block mapping table management unit 135 for managing the mapping relationship between the Physical Block Number (PBN) and Virtual Block Number (VBN) of the non-volatile memory 120 ; and a list storage unit 136 for storing an allocated block list and a free block list.
- PBN Physical Block Number
- VBN Virtual Block Number
- the block allocation unit 131 is adapted to allocate PBs to the fixed regions and non-fixed regions of the non-volatile memory 120 in accordance with the free block list stored in the list storage unit 136 .
- the free block list contains vacant PBs, in which no data exists.
- the PBs of the free block list may be sorted in the order of PBN, which is based on their wear level. Particularly, the PBN of the least frequently used PB is in the first position on the free block list, and that the PBN of the most frequently used PB is in the last position on the free block list.
- the free block list is generally stored in a spare region of the non-volatile memory 120 .
- the power interruption recovery unit 134 is adapted to reconstruct the free block list by using values stored in the spare region in the case of unexpected power interruption and rebooting, as will be described below in more detail.
- FIG. 3 shows a virtual block address space according to an exemplary embodiment of the present invention.
- the block allocation unit 131 may allocate VBNs of a virtual block address space to corresponding PBNs, as shown in FIG. 3 .
- the VBNs of the virtual block address space may successively map onto the PBNs of the non-volatile memory 120 in the opposite directions, in order to differentiate the fixed regions and the non-fixed regions from each other.
- Respective VBNs in the virtual block address space may consist of a number of pages, and the virtual block address space may have a size larger than that of the physical address space.
- the block allocation unit 131 then allocates the PB, which is in the first position on the free block list, to the fixed region or the non-fixed region.
- the block mapping table in which the mapping relationship between the PBN of the allocated PB and the VBN is recorded, may be stored in the block mapping table management unit 135 . As in the case of the virtual block address space, the block mapping table may similarly have successive allocation in the opposite directions, based on the fixed regions and the non-fixed regions.
- the block allocation unit 131 updates the allocated block list and the free block list, which are stored in the list storage unit 136 . Specifically, the block allocation unit 131 removes the PBs, which have been allocated to the fixed region or the non-fixed region, from the free block list and adds the allocated PBs to the last portion of the allocated block list.
- FIG. 4 shows an allocated block list and a free block list according to an exemplary embodiment of the present invention.
- the allocated block list 210 enumerates the PBNs of allocated PBs 230 in order of increasing wear level 231
- the free block list 220 enumerates the PBNs of unallocated PBs 230 in the same order.
- FIG. 5 shows a block mapping table, in which the PBNs on the allocated block list shown in FIG. 4 map onto VBNs, respectively.
- the PBNs successively map onto the VBNs in the opposite directions, based on the fixed regions and non-fixed regions.
- the metadata may be stored in a metadata storage unit 121 of the non-volatile memory 120 .
- the metadata stored in the metadata storage unit 121 may include, for instance, a Logical Block Address (LBA), fixed regions and non-fixed region data indicators, the wear level of blocks, and a restoration mark.
- LBA Logical Block Address
- the LBAs can be used for restoration after unexpected power interruption.
- the fixed region and the non-fixed region data indicators are used for differentiation between the fixed regions and the non-fixed regions, as well as restoration after power interruption.
- the wear level provides a standard for creating a free block list.
- the restoration mark is used for restoration after power interruption.
- a restoration mark may be made at the beginning of the free block list so that it is differentiated from the allocated block list.
- the block collection unit 132 counts effective pages of respective PBs on the allocated block list.
- the block collection unit 132 may perform block collection from a PB having the smallest number of effective pages. When a PB has the smallest number of effective pages, it can be said that the PB has the least amount of effective data. On this ground, block collection begins from the PB with the smallest number of effective pages.
- the block collection unit 132 allocates the PB that is in the first position on the free block list, so that the PB is positioned at the end of the allocated block list.
- the block collection unit 132 moves effective pages in a PB due for block collection to a block in the position of the allocated block list. After all effective pages are moved to the PB in the last position on the allocated block list, block collection unit 132 adds PBs, which have been subjected to block collection, to the free block list in the order of wear level.
- the block allocation unit 131 allocates the VBN of the virtual block address space to the PBN of the PB in the last position of the allocated block list so that the virtual block address space is updated.
- FIG. 6 shows PBs, before block collection, according to an exemplary embodiment of the present invention.
- the allocated block list 310 enumerates PBN 5 , PBN 0 , PBN 7 , and PBN 2 , the number of effective pages 311 of which are 5 , 4 , 6 , and 3 , respectively.
- the free block list 320 enumerates PBN 3 , PBN 6 , PBN 1 , and PBN 4 .
- the PBNs of the allocated block list 310 map onto respective VBNs in opposite directions, based on the fixed regions and the non-fixed regions.
- FIG. 7 shows PBs, after block collection, according to an exemplary embodiment of the present invention. It will be assumed in the following description with reference to FIG. 7 that, for the sake of block collection, the effective pages of PBN 0 shown in FIG. 6 are moved to PBN 6 , and those of PBN 2 and PBN 5 are moved to PBN 3 .
- PBN 7 retains its position, because it has not been subjected to block collection.
- PBN 3 and PBN 6 which have been subjected to block collection and have been moved from the free block list 320 to the allocated block list 310 , map onto new VBNs.
- the bad block management unit 133 When a bad block occurs in a PB on the allocated block list, the bad block management unit 133 removes that particular PB from the allocated block list and moves data, which had been recorded in the removed PB, to a PB which has been newly allocated from the free block list 320 . In order to move data that has been recorded in the bad block, the bad block management unit 133 inserts the PB, which has been newly allocated from the free block list, in the position of the removed bad block.
- FIG. 8 shows the occurrence of a bad block according to an exemplary embodiment of the present invention.
- the bad block management unit 133 receives a PB that is newly allocated from the free block list 420 and moves data, which has been recorded in the bad block, to the newly allocated PB. Before the bad block is removed, PBN 5 maps onto VBN 7 in the block mapping table 430 . After removal of the bad block, the newly allocated PB maps onto VBN 7 .
- FIG. 9 shows the removal of a bad block according to an exemplary embodiment of the present invention.
- the bad block management unit 133 moves data recorded in PBN 5 , which has a bad block, as shown in FIG. 8 , to PBN 6 , which has been newly allocated from the free block list 420 , and inserts PBN 6 in place of PBN 5 , which is neither,added to the free block list 420 nor is PBN 5 allocated.
- the block mapping table 430 newly allocated PBN 6 maps onto VBN 7 , which had previously mapped onto PBN 5 with a bad block.
- the power interruption recovery unit 134 is adapted to recover from unexpected power interruption by means of the allocated block list and the free block list. To this end, the power interruption recovery unit 134 stores the allocated block list and the free block list in the spare region of the non-volatile memory 120 , when both the allocated block list and the free block list change their order due to block collection or movement of data to the main storage medium 110 . Particularly, once the allocated block list and the free block list are stored, they retain their order even in the case of unexpected power interruption. As a result, the order of allocation of PBs remains intact and, based on the LBA in the spare region, the latest data can be extracted.
- the allocated block list and the free block list are stored only in the case of block collection or movement of data to the main storage medium 110 for easy restoration after power interruption.
- a restoration mark is made during block collection and is deleted during re-allocation, so that the allocated block list and the free block list can be differentiated.
- the block mapping table can also be restored by using the allocated block list.
- FIG. 10 shows a method of allocating blocks according to an exemplary embodiment of the present invention.
- the block allocation unit 131 initially selects PBs from the free block list to be newly allocated to the fixed region or the non-fixed region.
- the block allocation unit 131 newly allocates a PB in the first position on the free block list. This is because the free block list enumerates PBs in order of increasing wear level, and the foremost PB has the lowest wear level.
- the block allocation unit 131 allocates VBNs to the selected PBNs. Particularly, the VBNs are successively allocated in the virtual block address space in opposite directions, based on fixed regions and non-fixed regions.
- the block allocation unit 131 updates the block mapping table, which indicates the mapping relationship between the PBNs and the VBNs.
- the block allocation unit 131 adds the selected PBNs to the last of the allocated block list and, in operation (S 150 ), removes the selected PBNs from the free block list.
- the reason newly allocated PBNs are added to the last of the allocated block list is that, in the case of data update in a non-volatile memory 120 , PBs are newly allocated and added without modifying previously written data.
- PBNs are added to the last of the allocated block list in this manner every time new PBs are allocated, data written later may prove to be effective data. This can be used by the power interruption recovery unit 134 to recover from power interruption, as mentioned above.
- FIG. 11 shows a method of collecting blocks according to an exemplary embodiment of the present invention.
- the block collection unit 132 In operation (S 210 ), referring to the drawing, the block collection unit 132 initially counts effective pages included in respective PBs on the allocated block list. This is for the purpose of collecting PBs, which contain at least a predetermined number of non-effective pages, and for newly allocating them.
- the block collection unit 132 determines the order of PBs for block collection in accordance with the number of effective pages. It will be assumed in the following description of the present exemplary embodiment that block collection starts from a PB having the smallest number of effective pages. In addition, block collection is performed to PBs having less than a predetermined number of effective or vacant pages.
- the block collection unit 132 positions the foremost PBN on the free block list at the last of the allocated block list.
- the block collection unit 132 moves the effective pages of a PB due for block collection to the last PB on the allocated block list.
- the block collection unit 132 adds PBs, which are vacant after their effectives are moved, to the free block list based on wear level.
- the block collection unit 132 allocates VBNs to the PBNs that have been newly added to the allocated block list so that the block mapping table is updated.
- the block collection unit 132 determines whether or not all PBs due for block collection have been collected. If not, the block collection unit 132 performs operation (S 280 ) and then repeats the above-mentioned operations (S 240 ), (S 250 ) and (S 260 ) until all PBs due for block collection are collected. Particularly, in operation (S 280 ), the block collection unit 132 positions the foremost PB on the free block list at the last of the allocated block list for the sake of block collection of the next PB.
- the block collection unit 132 moves effective pages of a PB due for block collection to the last PB on the allocated block list; adds a PB, which is vacant after its effective pages have been moved, to the free block list based on wear level; and allocates a VBN to the PBN that has been newly added to the allocated block list so that the block mapping table is updated.
- FIG. 12 shows a method of processing bad blocks according to an exemplary embodiment of the present invention.
- the bad block management unit 133 initially determines whether or not any PB on the allocated block list has a bad block.
- the bad block management unit 133 receives a PB that has been newly allocated from the free block list by the block allocation unit 131 .
- the foremost PB on the free block list is newly allocated in consideration of its wear level. It can be easily understood by those skilled in the art that, although the foremost PB on the free block list is allocated in the present exemplary embodiment of the invention, a PB next to the foremost PB may be allocated in order to avoid frequent change of the foremost PB, on which a restoration mark is made as mentioned above.
- the bad block management unit 133 moves the data of the PB, which has a bad block, to the newly allocated PB.
- the bad block management unit 133 inserts the PB, to which data have moved, in the position of the PB with a bad block.
- the bad block management unit 133 assigns the VBN, which has been allocated to the PBN with a bad block, to a PBN inserted in the position of the PB with a bad block.
- FIG. 13 shows a method of recovering from power interruption according to an exemplary embodiment of the present invention.
- the power interruption recovery unit 134 extracts the allocated block list and the free block list, both of which have been stored in the spare region of the non-volatile memory 120 .
- the power interruption recovery unit 134 restores the order of PB allocation based on the allocated block list. When there is more than one PB having the same LBA, the power interruption unit 134 determines that the last written PB is effective.
- the power interruption recovery unit 134 restores the block mapping table based on the allocated block list.
- a unit refers to, but is not limited to, a software or hardware component, such as a Field Programmable Gate Array (FPGA) or an Application Specific Integrated Circuit (ASIC), which performs certain tasks.
- a unit may advantageously be configured to reside on the addressable storage medium and may be configured to execute on one or more processors.
- a unit may include, by way of example, components, such as software components, object-oriented software components, class components and task components, processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables.
- components such as software components, object-oriented software components, class components and task components, processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables.
- the functionality provided for in the components and units may be combined into fewer components and units or further separated into additional components and units.
- storage apparatuses using a non-volatile memory as a cache and methods of managing the same have the following exemplary advantages.
- the non-volatile memory is managed efficiently by dividing it into fixed regions and non-fixed regions according to whether or not data is fixed.
- the wear level of respective blocks becomes uniform by means of block collection in the non-volatile memory. This increases the life of the memory. In addition, reduced wear level of the main storage medium decreases the power consumption during its operation.
- the block mapping table can be restored from the allocated block list even in the case of unexpected power interruption, which guarantees safe data recovery.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Techniques For Improving Reliability Of Storages (AREA)
- Memory System (AREA)
- Memory System Of A Hierarchy Structure (AREA)
Abstract
Description
- This application claims priority from Korean Patent Application No. 10-2005-0130795 filed on Dec. 27, 2005 in the Korean Intellectual Property Office, the disclosure of which is incorporated herein by reference in its entirety.
- 1. Field of the invention
- Aspects of the present invention relate to storage apparatuses using a non-volatile memory as a cache and methods of managing the same. More particularly, aspects of the present invention relate to storage apparatuses using non-volatile memory, which retains data even after power interruption, as a cache and methods of managing the same.
- 2. Description of the Prior Art
- Referring to
FIG. 1 , aconventional storage apparatus 10 includes ahost 11, adata buffer 12, and amain storage medium 13. Thehost 11 transmits/receives data to/from themain storage medium 13 in accordance with a user's command. Thedata buffer 12 buffers the difference in rate between thehost 11 and themain storage medium 13. - Particularly, data transmitted from the
host 11 is temporarily stored in thedata buffer 12 until it is recorded in themain storage medium 13, and vice versa. Thedata buffer 12 of thestorage apparatus 10 is generally composed of a volatile memory. This means that, when power supply to themain storage device 10 is interrupted, all data existing in thedata buffer 12 is lost. - In order to increase access efficiency, the
storage apparatus 10 uses a cache, which stores a part of the data that is to be stored in themain storage medium 13. When thehost 11 reads data stored in the cache, access to themain storage medium 13 is unnecessary. This increases access efficiency. - However, the
data buffer 12 cannot be used as a cache, even when the size of thedata buffer 12 is increased, because it loses all data when the power supply is interrupted. In addition, the fact that themain storage medium 13 must be always supplied with power is an obstacle to reducing power consumption. - Therefore, it has recently been proposed to use a non-volatile memory as the cache of the
storage apparatus 10 so that, when thehost 11 reads/writes data from/to the non-volatile memory, power supply to themain storage medium 13 is interrupted so as to reduce the power consumption. - However, use of a non-volatile memory as the cache of the
storage apparatus 10 has the following problems: data must be efficiently managed according to whether or not it is fixed. Particularly, the non-volatile memory has a fixed region, in which data is fixedly positioned all the time, and a non-fixed region in which position of data is changed frequently. These regions must be managed efficiently. In addition, a method of protecting data against unexpected power interruption is necessary. There is also a need to provide a method of collecting blocks in order to minimize the time of power supply to themain storage medium 13, as well as a method of increasing the life of the non-volatile memory in consideration of the wear level of respective physical blocks in the non-volatile memory. - Laid-open Japanese Patent No. 2003-256289 discloses a system for maintaining the consistency of wear level of a flash memory system, the address of which can be designated as desired, by periodically deleting the designation of blocks, which have been grouped in the flash memory, according to a circular sequence (recording and deletion occur at both the bottom and top of a physical sector address). However, the system disclosed in Japanese Patent No. 2003-256289 does not propose a method of efficiently managing data in fixed and non-fixed regions, nor does it suggest protecting data against unexpected power interruption, or increasing lifespan based on block collection and wear level adjustment.
- Accordingly, exemplary embodiments of the present invention overcome the above-mentioned disadvantages occurring in the prior art, and other disadvantages not described above. Also, the present invention is not required to overcome the disadvantages described above, and an exemplary embodiment of the present invention may not overcome any of the problems described above. An aspect of the present invention provides a storage apparatus using a non-volatile memory as its cache in such a manner that the non-volatile memory is separately managed by dividing it into fixed and non-fixed regions in accordance with whether or not data is fixed in the regions and blocks are collected for uniform wear level of the blocks, as well as a method of managing the same.
- Another aspect of the present invention provides a storage apparatus using a non-volatile memory as its cache for easy recovery from unexpected power interruption and a method for managing the same.
- In order to accomplish these objects, and others, there is provided a storage apparatus using a non-volatile memory as a cache, the apparatus including a main storage medium; a non-volatile memory used as a cache of the main storage medium, a region of the non-volatile memory being divided into a fixed region and a non-fixed region according to whether or not data is fixed; and a block management unit managing physical blocks by means of virtual addresses, the physical blocks being allocated to the non-volatile memory.
- In accordance with another aspect of the present invention, there is provided a method of managing a storage apparatus using a non-volatile memory as a cache, the method including dividing a region of a non-volatile memory used as a cache of a main storage medium into a fixed region and a non-fixed region according to whether or not data is fixed and managing physical blocks allocated to the fixed region and the non-fixed region by means of virtual addresses allocated to the physical blocks, respectively.
- The above aspects of the present invention, and others, will become more apparent from the following detailed description with reference to the accompanying drawings, in which:
-
FIG. 1 shows a conventional storage apparatus; -
FIG. 2 shows a storage apparatus using a non-volatile memory as its cache according to an exemplary embodiment of the present invention; -
FIG. 3 shows a virtual block address space according to an exemplary embodiment of the present invention; -
FIG. 4 shows an allocated block list and a free block list according to an exemplary embodiment of the present invention; -
FIG. 5 shows a block mapping table according to an exemplary embodiment of the present invention; -
FIG. 6 shows an allocated block list, a free block list, and a block mapping table, before blocks are collected, according to an exemplary embodiment of the present invention; -
FIG. 7 shows an allocated block list, a free block list, and a block mapping table, after blocks are collected, according to an exemplary embodiment of the present invention; -
FIG. 8 shows an allocated block list, a free block list, and a block mapping table, before a bad block is processed, according to an exemplary embodiment of the present invention; -
FIG. 9 shows an allocated block list, a free block list, and a block mapping table, after a bad block is processed, according to an exemplary embodiment of the present invention; -
FIG. 10 shows a method of allocating blocks according to an exemplary embodiment of the present invention; -
FIG. 11 shows a method of collecting blocks according to an exemplary embodiment of the present invention; -
FIG. 12 shows a method of processing a bad block according to an exemplary embodiment of the present invention; and -
FIG. 13 shows a method of recovering from power interruption according to an exemplary embodiment of the present invention. - Hereinafter, exemplary embodiments of the present invention will be described with reference to the accompanying drawings. The matters defined in the description such as a detailed construction and elements are nothing but examples provided to assist in a comprehensive understanding of the invention. Thus, it is apparent that the present invention can be carried out without those defined matters. In the following description of the exemplary embodiments of the present invention, the same drawing reference numerals are used for the same elements even in different drawings. Also, a detailed description of known functions and configurations incorporated herein will be omitted when it may obscure the subject matter of the present invention.
- Exemplary embodiments of the present invention are described hereinafter with reference to flowchart illustrations relating to a storage apparatus using a non-volatile memory as its cache and a method of managing the same according to exemplary embodiments of the invention. It will be understood that each block of the flowchart illustrations, and combinations of blocks in the flowchart illustrations, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart block or blocks.
- These computer program instructions may also be stored in a computer usable or computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer usable or computer-readable memory produce an article of manufacture including instruction means that implement the functions specified in the flowchart block or blocks.
- The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.
- And, each block of the flowchart illustrations may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks may occur out of the order shown. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
-
FIG. 2 shows a storage apparatus using a non-volatile memory as its cache according to an exemplary embodiment of the present invention. - As shown, a
storage apparatus 100 using a non-volatile memory as its cache according to an exemplary embodiment of the present invention may include amain storage medium 110, anon-volatile memory 120 used as the cache of themain storage medium 110, and ablock management unit 130 for managing the Physical Block (PB) of thenon-volatile memory 120 by means of virtual addresses. - It will be understood by those skilled in the art that, according to the present exemplary embodiment, the
main storage medium 110 is a large-capacity storage medium, such as a hard disk drive, and thenon-volatile memory 120 is, for example, a flash memory capable of retaining data even in the case of power interruption. Thestorage apparatus 100 using a non-volatile memory as its cache according to the present exemplary embodiment may be connected to ahost 140, which transmits/receives data to/from themain storage medium 110 in accordance with the user's command. Thehost 140, in turn, may be connected to theblock management unit 130. - The
non-volatile memory 120 may be divided into a fixed region in which data is fixed and a non-volatile region in which data is changed frequently. The fixed region stores data that is supposed to permanently reside in thenon-volatile memory 120 and is used as the cache of themain storage apparatus 110. In the non-fixed region, data frequently moves to/from themain storage medium 110. - The
block management unit 130 may include ablock allocation unit 131 for allocating PBs to thenon-volatile memory 120; ablock collection unit 132 for collecting allocated PBs; a badblock management unit 133 for managing bad blocks; a powerinterruption recovery unit 134 for recovering from power interruption; a block mappingtable management unit 135 for managing the mapping relationship between the Physical Block Number (PBN) and Virtual Block Number (VBN) of thenon-volatile memory 120; and alist storage unit 136 for storing an allocated block list and a free block list. - The
block allocation unit 131 is adapted to allocate PBs to the fixed regions and non-fixed regions of thenon-volatile memory 120 in accordance with the free block list stored in thelist storage unit 136. The free block list contains vacant PBs, in which no data exists. The PBs of the free block list may be sorted in the order of PBN, which is based on their wear level. Particularly, the PBN of the least frequently used PB is in the first position on the free block list, and that the PBN of the most frequently used PB is in the last position on the free block list. The free block list is generally stored in a spare region of thenon-volatile memory 120. The powerinterruption recovery unit 134 is adapted to reconstruct the free block list by using values stored in the spare region in the case of unexpected power interruption and rebooting, as will be described below in more detail. -
FIG. 3 shows a virtual block address space according to an exemplary embodiment of the present invention. - In order to allocate PBs to the fixed regions and the non-fixed regions of the
non-volatile memory 120, theblock allocation unit 131 may allocate VBNs of a virtual block address space to corresponding PBNs, as shown inFIG. 3 . The VBNs of the virtual block address space may successively map onto the PBNs of thenon-volatile memory 120 in the opposite directions, in order to differentiate the fixed regions and the non-fixed regions from each other. Respective VBNs in the virtual block address space may consist of a number of pages, and the virtual block address space may have a size larger than that of the physical address space. - The
block allocation unit 131 then allocates the PB, which is in the first position on the free block list, to the fixed region or the non-fixed region. The block mapping table, in which the mapping relationship between the PBN of the allocated PB and the VBN is recorded, may be stored in the block mappingtable management unit 135. As in the case of the virtual block address space, the block mapping table may similarly have successive allocation in the opposite directions, based on the fixed regions and the non-fixed regions. After allocating some PBs on the free block list to the fixed region or the non-fixed region, theblock allocation unit 131 updates the allocated block list and the free block list, which are stored in thelist storage unit 136. Specifically, theblock allocation unit 131 removes the PBs, which have been allocated to the fixed region or the non-fixed region, from the free block list and adds the allocated PBs to the last portion of the allocated block list. -
FIG. 4 shows an allocated block list and a free block list according to an exemplary embodiment of the present invention. - It is clear from the drawing that, according to the present exemplary embodiment, the allocated
block list 210 enumerates the PBNs of allocatedPBs 230 in order of increasingwear level 231, and thefree block list 220 enumerates the PBNs ofunallocated PBs 230 in the same order. -
FIG. 5 shows a block mapping table, in which the PBNs on the allocated block list shown inFIG. 4 map onto VBNs, respectively. - It is clear from the drawing that, in the block mapping table 240 according to the present exemplary embodiment, the PBNs successively map onto the VBNs in the opposite directions, based on the fixed regions and non-fixed regions.
- When data is recorded in the
non-volatile memory 120, various types of metadata can be stored in the spare region together with the data. According to the present exemplary embodiment, the metadata may be stored in ametadata storage unit 121 of thenon-volatile memory 120. The metadata stored in themetadata storage unit 121 may include, for instance, a Logical Block Address (LBA), fixed regions and non-fixed region data indicators, the wear level of blocks, and a restoration mark. - When LBAs map onto respective PBs of the allocated block list, the LBAs can be used for restoration after unexpected power interruption. The fixed region and the non-fixed region data indicators are used for differentiation between the fixed regions and the non-fixed regions, as well as restoration after power interruption. The wear level provides a standard for creating a free block list. The restoration mark is used for restoration after power interruption. Particularly, when the allocated block list and the free block list are connected and stored together in the
non-volatile memory 120, a restoration mark may be made at the beginning of the free block list so that it is differentiated from the allocated block list. Those skilled in the art can understand that, when the allocated block list and the free block list are connected and stored together, they actually constitute a single list with a restoration mark made at the beginning of the free block list for differentiation between them. - The
block collection unit 132 counts effective pages of respective PBs on the allocated block list. Theblock collection unit 132 may perform block collection from a PB having the smallest number of effective pages. When a PB has the smallest number of effective pages, it can be said that the PB has the least amount of effective data. On this ground, block collection begins from the PB with the smallest number of effective pages. - The
block collection unit 132 allocates the PB that is in the first position on the free block list, so that the PB is positioned at the end of the allocated block list. Theblock collection unit 132 moves effective pages in a PB due for block collection to a block in the position of the allocated block list. After all effective pages are moved to the PB in the last position on the allocated block list,block collection unit 132 adds PBs, which have been subjected to block collection, to the free block list in the order of wear level. - For the sake of block collection, the
block allocation unit 131 allocates the VBN of the virtual block address space to the PBN of the PB in the last position of the allocated block list so that the virtual block address space is updated. -
FIG. 6 shows PBs, before block collection, according to an exemplary embodiment of the present invention. - It is clear from the drawing that the allocated
block list 310 enumeratesPBN 5,PBN 0,PBN 7, andPBN 2, the number ofeffective pages 311 of which are 5, 4, 6, and 3, respectively. Thefree block list 320 enumeratesPBN 3,PBN 6,PBN 1, andPBN 4. In the block mapping table 330, the PBNs of the allocatedblock list 310 map onto respective VBNs in opposite directions, based on the fixed regions and the non-fixed regions. -
FIG. 7 shows PBs, after block collection, according to an exemplary embodiment of the present invention. It will be assumed in the following description with reference toFIG. 7 that, for the sake of block collection, the effective pages ofPBN 0 shown inFIG. 6 are moved toPBN 6, and those ofPBN 2 andPBN 5 are moved toPBN 3. - It is clear from
FIG. 7 thatPBN 0,PBN 2, and PBN 5 (shown inFIG. 6 ) have been removed from the allocatedblock list 310 as a result of block collection and have been added to thefree block list 320 in the order of wear level. - As shown in
FIG. 7 , in the block mapping table 330,PBN 7 retains its position, because it has not been subjected to block collection. In contrast,PBN 3 andPBN 6, which have been subjected to block collection and have been moved from thefree block list 320 to the allocatedblock list 310, map onto new VBNs. - When a bad block occurs in a PB on the allocated block list, the bad
block management unit 133 removes that particular PB from the allocated block list and moves data, which had been recorded in the removed PB, to a PB which has been newly allocated from thefree block list 320. In order to move data that has been recorded in the bad block, the badblock management unit 133 inserts the PB, which has been newly allocated from the free block list, in the position of the removed bad block. -
FIG. 8 shows the occurrence of a bad block according to an exemplary embodiment of the present invention. - As shown in
FIG. 8 , when a bad block occurs inPBN 5 of the allocatedblock list 410, the badblock management unit 133 receives a PB that is newly allocated from thefree block list 420 and moves data, which has been recorded in the bad block, to the newly allocated PB. Before the bad block is removed,PBN 5 maps ontoVBN 7 in the block mapping table 430. After removal of the bad block, the newly allocated PB maps ontoVBN 7. -
FIG. 9 shows the removal of a bad block according to an exemplary embodiment of the present invention. - As shown in
FIG. 9 , the badblock management unit 133 moves data recorded inPBN 5, which has a bad block, as shown inFIG. 8 , toPBN 6, which has been newly allocated from thefree block list 420, and insertsPBN 6 in place ofPBN 5, which is neither,added to thefree block list 420 nor isPBN 5 allocated. In the block mapping table 430, newly allocatedPBN 6 maps ontoVBN 7, which had previously mapped ontoPBN 5 with a bad block. - The power
interruption recovery unit 134 is adapted to recover from unexpected power interruption by means of the allocated block list and the free block list. To this end, the powerinterruption recovery unit 134 stores the allocated block list and the free block list in the spare region of thenon-volatile memory 120, when both the allocated block list and the free block list change their order due to block collection or movement of data to themain storage medium 110. Particularly, once the allocated block list and the free block list are stored, they retain their order even in the case of unexpected power interruption. As a result, the order of allocation of PBs remains intact and, based on the LBA in the spare region, the latest data can be extracted. As such, the allocated block list and the free block list are stored only in the case of block collection or movement of data to themain storage medium 110 for easy restoration after power interruption. A restoration mark is made during block collection and is deleted during re-allocation, so that the allocated block list and the free block list can be differentiated. The block mapping table can also be restored by using the allocated block list. -
FIG. 10 shows a method of allocating blocks according to an exemplary embodiment of the present invention. - Referring to the drawing, in operation (S110) the
block allocation unit 131 initially selects PBs from the free block list to be newly allocated to the fixed region or the non-fixed region. Theblock allocation unit 131 newly allocates a PB in the first position on the free block list. This is because the free block list enumerates PBs in order of increasing wear level, and the foremost PB has the lowest wear level. - In operation (S120), the
block allocation unit 131 allocates VBNs to the selected PBNs. Particularly, the VBNs are successively allocated in the virtual block address space in opposite directions, based on fixed regions and non-fixed regions. - In operation (S130), the
block allocation unit 131 updates the block mapping table, which indicates the mapping relationship between the PBNs and the VBNs. - In operation (S140), the
block allocation unit 131 adds the selected PBNs to the last of the allocated block list and, in operation (S150), removes the selected PBNs from the free block list. The reason newly allocated PBNs are added to the last of the allocated block list is that, in the case of data update in anon-volatile memory 120, PBs are newly allocated and added without modifying previously written data. When PBNs are added to the last of the allocated block list in this manner every time new PBs are allocated, data written later may prove to be effective data. This can be used by the powerinterruption recovery unit 134 to recover from power interruption, as mentioned above. -
FIG. 11 shows a method of collecting blocks according to an exemplary embodiment of the present invention. - In operation (S210), referring to the drawing, the
block collection unit 132 initially counts effective pages included in respective PBs on the allocated block list. This is for the purpose of collecting PBs, which contain at least a predetermined number of non-effective pages, and for newly allocating them. - In operation (S220), the
block collection unit 132 determines the order of PBs for block collection in accordance with the number of effective pages. It will be assumed in the following description of the present exemplary embodiment that block collection starts from a PB having the smallest number of effective pages. In addition, block collection is performed to PBs having less than a predetermined number of effective or vacant pages. - In operation (S230), in order to collect a PB having the smallest number of effective pages in the determined order, the
block collection unit 132 positions the foremost PBN on the free block list at the last of the allocated block list. - In operation (S240), the
block collection unit 132 moves the effective pages of a PB due for block collection to the last PB on the allocated block list. In operation (S250), theblock collection unit 132 adds PBs, which are vacant after their effectives are moved, to the free block list based on wear level. In operation (S260), theblock collection unit 132 allocates VBNs to the PBNs that have been newly added to the allocated block list so that the block mapping table is updated. - In operation (S270), the
block collection unit 132 determines whether or not all PBs due for block collection have been collected. If not, theblock collection unit 132 performs operation (S280) and then repeats the above-mentioned operations (S240), (S250) and (S260) until all PBs due for block collection are collected. Particularly, in operation (S280), theblock collection unit 132 positions the foremost PB on the free block list at the last of the allocated block list for the sake of block collection of the next PB. Then, theblock collection unit 132 moves effective pages of a PB due for block collection to the last PB on the allocated block list; adds a PB, which is vacant after its effective pages have been moved, to the free block list based on wear level; and allocates a VBN to the PBN that has been newly added to the allocated block list so that the block mapping table is updated. -
FIG. 12 shows a method of processing bad blocks according to an exemplary embodiment of the present invention. - Referring to
FIG. 12 , in operation (S310) the badblock management unit 133 initially determines whether or not any PB on the allocated block list has a bad block. - If so, in operation (S320) the bad
block management unit 133 receives a PB that has been newly allocated from the free block list by theblock allocation unit 131. Particularly, the foremost PB on the free block list is newly allocated in consideration of its wear level. It can be easily understood by those skilled in the art that, although the foremost PB on the free block list is allocated in the present exemplary embodiment of the invention, a PB next to the foremost PB may be allocated in order to avoid frequent change of the foremost PB, on which a restoration mark is made as mentioned above. - After a new PB is allocated, in operation (S330) the bad
block management unit 133 moves the data of the PB, which has a bad block, to the newly allocated PB. - After data movement, in operation (S340) the bad
block management unit 133 inserts the PB, to which data have moved, in the position of the PB with a bad block. - In operation (S350), the bad
block management unit 133 assigns the VBN, which has been allocated to the PBN with a bad block, to a PBN inserted in the position of the PB with a bad block. -
FIG. 13 shows a method of recovering from power interruption according to an exemplary embodiment of the present invention. - Referring to
FIG. 13 , in operation (S410), when power interruption occurs unexpectedly, the powerinterruption recovery unit 134 extracts the allocated block list and the free block list, both of which have been stored in the spare region of thenon-volatile memory 120. - In operation (S420), the power
interruption recovery unit 134 restores the order of PB allocation based on the allocated block list. When there is more than one PB having the same LBA, thepower interruption unit 134 determines that the last written PB is effective. - In operation (S430), the power
interruption recovery unit 134 restores the block mapping table based on the allocated block list. - The term “unit,” as used herein, refers to, but is not limited to, a software or hardware component, such as a Field Programmable Gate Array (FPGA) or an Application Specific Integrated Circuit (ASIC), which performs certain tasks. A unit may advantageously be configured to reside on the addressable storage medium and may be configured to execute on one or more processors. Thus, a unit may include, by way of example, components, such as software components, object-oriented software components, class components and task components, processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. The functionality provided for in the components and units may be combined into fewer components and units or further separated into additional components and units.
- As mentioned above, storage apparatuses using a non-volatile memory as a cache and methods of managing the same, consistent with exemplary embodiments of the present invention, have the following exemplary advantages.
- The non-volatile memory is managed efficiently by dividing it into fixed regions and non-fixed regions according to whether or not data is fixed.
- The wear level of respective blocks becomes uniform by means of block collection in the non-volatile memory. This increases the life of the memory. In addition, reduced wear level of the main storage medium decreases the power consumption during its operation.
- The block mapping table can be restored from the allocated block list even in the case of unexpected power interruption, which guarantees safe data recovery.
- Although exemplary embodiments of the present invention have been described above for illustrative purposes, those skilled in the art will appreciate that various modifications, additions and substitutions are possible, without departing from the scope and spirit of the invention as disclosed in the accompanying claims.
Claims (24)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR10-2005-0130795 | 2005-12-27 | ||
KR1020050130795A KR100755700B1 (en) | 2005-12-27 | 2005-12-27 | Storage apparatus using non volatile memory and method for managing the same |
Publications (2)
Publication Number | Publication Date |
---|---|
US20070150654A1 true US20070150654A1 (en) | 2007-06-28 |
US7774541B2 US7774541B2 (en) | 2010-08-10 |
Family
ID=37890869
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/601,819 Active 2027-08-19 US7774541B2 (en) | 2005-12-27 | 2006-11-20 | Storage apparatus using non-volatile memory as cache and method of managing the same |
Country Status (5)
Country | Link |
---|---|
US (1) | US7774541B2 (en) |
EP (1) | EP1804168A1 (en) |
JP (1) | JP2007179545A (en) |
KR (1) | KR100755700B1 (en) |
CN (1) | CN100524249C (en) |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070150647A1 (en) * | 2005-12-27 | 2007-06-28 | Samsung Electronics Co., Ltd. | Storage apparatus using non-volatile memory as cache and method of operating the same |
US20110010582A1 (en) * | 2009-07-09 | 2011-01-13 | Fujitsu Limited | Storage system, evacuation processing device and method of controlling evacuation processing device |
US20110016285A1 (en) * | 2009-07-16 | 2011-01-20 | Samsung Electronics Co., Ltd. | Apparatus and method for scratch pad memory management |
US20110107033A1 (en) * | 2009-11-04 | 2011-05-05 | Nokia Corporation | Method and apparatus for providing an application-level cache |
US20110119569A1 (en) * | 2009-11-18 | 2011-05-19 | Samsung Electronics Co., Ltd. | Apparatus and method for storing data using non-volatile buffer |
WO2011081232A1 (en) * | 2009-12-29 | 2011-07-07 | 주식회사 프롬나이 | Computing system and method for selectively implementing process persistence using nvram and volatile ram |
US20120254531A1 (en) * | 2011-03-28 | 2012-10-04 | Fujitsu Limited | Storage apparatus and storage control device |
US20130024607A1 (en) * | 2011-07-19 | 2013-01-24 | Young-Ho Park | Memory apparatus |
US20140068157A1 (en) * | 2012-08-29 | 2014-03-06 | Buffalo Memory Co., Ltd. | Solid-state drive device |
US8898376B2 (en) | 2012-06-04 | 2014-11-25 | Fusion-Io, Inc. | Apparatus, system, and method for grouping data stored on an array of solid-state storage elements |
US9063874B2 (en) | 2008-11-10 | 2015-06-23 | SanDisk Technologies, Inc. | Apparatus, system, and method for wear management |
US9164856B2 (en) | 2013-11-11 | 2015-10-20 | International Business Machines Corporation | Persistent messaging mechanism |
US9170897B2 (en) | 2012-05-29 | 2015-10-27 | SanDisk Technologies, Inc. | Apparatus, system, and method for managing solid-state storage reliability |
US20150331807A1 (en) * | 2014-12-10 | 2015-11-19 | Advanced Micro Devices, Inc. | Thin provisioning architecture for high seek-time devices |
US9342419B2 (en) | 2013-11-11 | 2016-05-17 | Globalfoundries Inc. | Persistent messaging mechanism |
WO2016122491A1 (en) * | 2015-01-28 | 2016-08-04 | Hewlett-Packard Development Company, L.P. | Page cache in a non-volatile memory |
EP3361387A4 (en) * | 2015-10-21 | 2018-10-17 | Huawei Technologies Co., Ltd. | Data transmission method, equipment and system |
US20190220402A1 (en) * | 2018-01-18 | 2019-07-18 | EMC IP Holding Company LLC | Data recovery method, data recovery system, and computer program product |
Families Citing this family (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100908637B1 (en) * | 2007-10-10 | 2009-07-21 | 한양대학교 산학협력단 | How to manage data in flash memory |
JP4961319B2 (en) * | 2007-10-11 | 2012-06-27 | 株式会社日立製作所 | A storage system that dynamically allocates real areas to virtual areas in virtual volumes |
US8074145B2 (en) * | 2007-11-12 | 2011-12-06 | Harris Corporation | Memory system and related method using software-defined radio with write-protected, non-volatile memory |
US9612954B2 (en) | 2008-12-31 | 2017-04-04 | Micron Technology, Inc. | Recovery for non-volatile memory after power loss |
KR20100091544A (en) * | 2009-02-10 | 2010-08-19 | 삼성전자주식회사 | Memory system and wear leveling method thereof |
US9076239B2 (en) * | 2009-04-30 | 2015-07-07 | Stmicroelectronics S.R.L. | Method and systems for thumbnail generation, and corresponding computer program product |
KR100950937B1 (en) * | 2009-06-30 | 2010-04-08 | 주식회사 셀픽 | Cache memory of solid state disk and system for managing chche using it |
US8402242B2 (en) * | 2009-07-29 | 2013-03-19 | International Business Machines Corporation | Write-erase endurance lifetime of memory storage devices |
KR101717644B1 (en) * | 2009-09-08 | 2017-03-27 | 샌디스크 테크놀로지스 엘엘씨 | Apparatus, system, and method for caching data on a solid-state storage device |
CN102576333B (en) * | 2009-10-05 | 2016-01-13 | 马维尔国际贸易有限公司 | Data cache in nonvolatile memory |
US8417878B2 (en) * | 2010-09-20 | 2013-04-09 | Seagate Technology Llc | Selection of units for garbage collection in flash memory |
CN103186471B (en) * | 2011-12-30 | 2016-10-12 | 深圳市共进电子股份有限公司 | The management method of bad block and system in storage device |
KR101993704B1 (en) | 2012-08-24 | 2019-06-27 | 삼성전자주식회사 | Storage device based on a flash memory and method for allocatting write memory block of memory controller controlling a flash memory |
US9032244B2 (en) * | 2012-11-16 | 2015-05-12 | Microsoft Technology Licensing, Llc | Memory segment remapping to address fragmentation |
KR102002921B1 (en) * | 2012-12-05 | 2019-07-23 | 삼성전자주식회사 | Buffer managing method and therefore semiconductor storage device |
JP5714681B2 (en) * | 2013-10-25 | 2015-05-07 | ウィンボンド エレクトロニクス コーポレーション | Semiconductor memory device |
KR101573375B1 (en) | 2013-10-31 | 2015-12-03 | 전자부품연구원 | Locality-aware SSD Cache Module based on Server Environment |
CN104851457B (en) * | 2014-02-18 | 2019-01-08 | 华邦电子股份有限公司 | Semiconductor storage |
US10289551B2 (en) * | 2017-05-11 | 2019-05-14 | Western Digital Technologies, Inc. | Preserving data upon a power shutdown |
CN107688442B (en) * | 2017-09-04 | 2020-11-20 | 苏州浪潮智能科技有限公司 | Virtual block management method for solid state disk |
KR20200126531A (en) | 2019-04-30 | 2020-11-09 | 에스케이하이닉스 주식회사 | Memory system and method of performing command operation thereof |
Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5404485A (en) * | 1993-03-08 | 1995-04-04 | M-Systems Flash Disk Pioneers Ltd. | Flash file system |
US5485595A (en) * | 1993-03-26 | 1996-01-16 | Cirrus Logic, Inc. | Flash memory mass storage architecture incorporating wear leveling technique without using cam cells |
US5568423A (en) * | 1995-04-14 | 1996-10-22 | Unisys Corporation | Flash memory wear leveling system providing immediate direct access to microprocessor |
US5832493A (en) * | 1997-04-24 | 1998-11-03 | Trimble Navigation Limited | Flash file management system |
US5860082A (en) * | 1996-03-28 | 1999-01-12 | Datalight, Inc. | Method and apparatus for allocating storage in a flash memory |
US5860083A (en) * | 1996-11-26 | 1999-01-12 | Kabushiki Kaisha Toshiba | Data storage system having flash memory and disk drive |
US5907856A (en) * | 1995-07-31 | 1999-05-25 | Lexar Media, Inc. | Moving sectors within a block of information in a flash memory mass storage architecture |
US5937425A (en) * | 1997-10-16 | 1999-08-10 | M-Systems Flash Disk Pioneers Ltd. | Flash file system optimized for page-mode flash technologies |
US20020013879A1 (en) * | 1998-03-18 | 2002-01-31 | Sang-Wook Han | Flash memory array access method and device |
US20030225961A1 (en) * | 2002-06-03 | 2003-12-04 | James Chow | Flash memory management system and method |
US20040168018A1 (en) * | 2002-02-27 | 2004-08-26 | Aasheim Jered Donald | Free sector manager for data stored in flash memory devices |
US20040205314A1 (en) * | 2003-02-18 | 2004-10-14 | Stmicroelectronics S.R.L. | Semiconductor memory with access protection scheme |
US20050132126A1 (en) * | 2003-12-15 | 2005-06-16 | Lin Lin | Method and file structures for managing data on a flash disk |
US20050132129A1 (en) * | 2001-08-28 | 2005-06-16 | International Business Machines Corporation | Data management in flash memory |
US20050182892A1 (en) * | 2003-03-19 | 2005-08-18 | Kenichi Nakanishi | Data storage device, method for updating management information in data storage device, and computer program |
US20050204187A1 (en) * | 2004-03-11 | 2005-09-15 | Lee Charles C. | System and method for managing blocks in flash memory |
US20050246487A1 (en) * | 2004-05-03 | 2005-11-03 | Microsoft Corporation | Non-volatile memory cache performance improvement |
US20050273550A1 (en) * | 2002-10-24 | 2005-12-08 | Micron Technology, Inc. | Permanent memory block protection in a flash memory device |
US20060288153A1 (en) * | 2005-06-21 | 2006-12-21 | Katsuya Tanaka | Storage system using flash memory |
US20070150647A1 (en) * | 2005-12-27 | 2007-06-28 | Samsung Electronics Co., Ltd. | Storage apparatus using non-volatile memory as cache and method of operating the same |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5414826A (en) | 1990-01-31 | 1995-05-09 | Hewlett-Packard Company | System and method for memory management in microcomputer |
JPH0511933A (en) | 1991-07-08 | 1993-01-22 | Kawasaki Steel Corp | Hard disk emulator and fixed cache area allocating method for the emulator |
EP0541319B1 (en) | 1991-11-04 | 1997-05-02 | Sun Microsystems, Inc. | Write through virtual cache memory, alias addressing, and cache flushes |
JP3070453B2 (en) | 1995-09-20 | 2000-07-31 | 日本電気株式会社 | Memory failure recovery method and recovery system for computer system |
JPH09128302A (en) | 1995-11-01 | 1997-05-16 | Fujitsu Ltd | Data access method to non-volatile memory |
JP3868585B2 (en) | 1996-07-30 | 2007-01-17 | シャープ株式会社 | Memory management device and computer-readable recording medium |
JPH1153261A (en) | 1997-08-07 | 1999-02-26 | Toshiba Corp | Data storage system, and cache control method applied to the system |
US20030163633A1 (en) | 2002-02-27 | 2003-08-28 | Aasheim Jered Donald | System and method for achieving uniform wear levels in a flash memory device |
WO2004059624A1 (en) | 2002-12-24 | 2004-07-15 | Lg Electronics, Inc. | Dual journaling store method and storage medium thereof |
KR100514756B1 (en) * | 2003-12-23 | 2005-09-14 | 삼성전자주식회사 | Cash processing method for writing in flash memory using file system |
-
2005
- 2005-12-27 KR KR1020050130795A patent/KR100755700B1/en active IP Right Grant
-
2006
- 2006-11-20 US US11/601,819 patent/US7774541B2/en active Active
- 2006-12-20 JP JP2006342259A patent/JP2007179545A/en active Pending
- 2006-12-22 EP EP06127067A patent/EP1804168A1/en not_active Withdrawn
- 2006-12-26 CN CNB2006101682319A patent/CN100524249C/en active Active
Patent Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5404485A (en) * | 1993-03-08 | 1995-04-04 | M-Systems Flash Disk Pioneers Ltd. | Flash file system |
US5485595A (en) * | 1993-03-26 | 1996-01-16 | Cirrus Logic, Inc. | Flash memory mass storage architecture incorporating wear leveling technique without using cam cells |
US5568423A (en) * | 1995-04-14 | 1996-10-22 | Unisys Corporation | Flash memory wear leveling system providing immediate direct access to microprocessor |
US5907856A (en) * | 1995-07-31 | 1999-05-25 | Lexar Media, Inc. | Moving sectors within a block of information in a flash memory mass storage architecture |
US5860082A (en) * | 1996-03-28 | 1999-01-12 | Datalight, Inc. | Method and apparatus for allocating storage in a flash memory |
US5860083A (en) * | 1996-11-26 | 1999-01-12 | Kabushiki Kaisha Toshiba | Data storage system having flash memory and disk drive |
US5832493A (en) * | 1997-04-24 | 1998-11-03 | Trimble Navigation Limited | Flash file management system |
US5937425A (en) * | 1997-10-16 | 1999-08-10 | M-Systems Flash Disk Pioneers Ltd. | Flash file system optimized for page-mode flash technologies |
US20020013879A1 (en) * | 1998-03-18 | 2002-01-31 | Sang-Wook Han | Flash memory array access method and device |
US20050132129A1 (en) * | 2001-08-28 | 2005-06-16 | International Business Machines Corporation | Data management in flash memory |
US20040168018A1 (en) * | 2002-02-27 | 2004-08-26 | Aasheim Jered Donald | Free sector manager for data stored in flash memory devices |
US20030225961A1 (en) * | 2002-06-03 | 2003-12-04 | James Chow | Flash memory management system and method |
US20050273550A1 (en) * | 2002-10-24 | 2005-12-08 | Micron Technology, Inc. | Permanent memory block protection in a flash memory device |
US20040205314A1 (en) * | 2003-02-18 | 2004-10-14 | Stmicroelectronics S.R.L. | Semiconductor memory with access protection scheme |
US20050182892A1 (en) * | 2003-03-19 | 2005-08-18 | Kenichi Nakanishi | Data storage device, method for updating management information in data storage device, and computer program |
US20050132126A1 (en) * | 2003-12-15 | 2005-06-16 | Lin Lin | Method and file structures for managing data on a flash disk |
US20050204187A1 (en) * | 2004-03-11 | 2005-09-15 | Lee Charles C. | System and method for managing blocks in flash memory |
US20050246487A1 (en) * | 2004-05-03 | 2005-11-03 | Microsoft Corporation | Non-volatile memory cache performance improvement |
US20060288153A1 (en) * | 2005-06-21 | 2006-12-21 | Katsuya Tanaka | Storage system using flash memory |
US20070150647A1 (en) * | 2005-12-27 | 2007-06-28 | Samsung Electronics Co., Ltd. | Storage apparatus using non-volatile memory as cache and method of operating the same |
Cited By (31)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7716422B2 (en) | 2005-12-27 | 2010-05-11 | Samsung Electronics Co., Ltd. | Storage apparatus and method for using a non-volatile cache memory organized into stationary and non-stationary circular regions |
US20070150647A1 (en) * | 2005-12-27 | 2007-06-28 | Samsung Electronics Co., Ltd. | Storage apparatus using non-volatile memory as cache and method of operating the same |
US9063874B2 (en) | 2008-11-10 | 2015-06-23 | SanDisk Technologies, Inc. | Apparatus, system, and method for wear management |
US20110010582A1 (en) * | 2009-07-09 | 2011-01-13 | Fujitsu Limited | Storage system, evacuation processing device and method of controlling evacuation processing device |
KR101615659B1 (en) * | 2009-07-16 | 2016-05-12 | 삼성전자주식회사 | Apparatus and method for scratch pad memory management |
US20110016285A1 (en) * | 2009-07-16 | 2011-01-20 | Samsung Electronics Co., Ltd. | Apparatus and method for scratch pad memory management |
US9152547B2 (en) * | 2009-07-16 | 2015-10-06 | Samsung Electronics Co., Ltd. | Apparatus and method for scratch pad memory management |
US20110107033A1 (en) * | 2009-11-04 | 2011-05-05 | Nokia Corporation | Method and apparatus for providing an application-level cache |
US8301838B2 (en) | 2009-11-04 | 2012-10-30 | Nokia Corporation | Method and apparatus for providing an application-level cache with a locked region and a floating region |
US8423865B2 (en) | 2009-11-18 | 2013-04-16 | Samsung Electronics Co., Ltd. | Apparatus and method for storing data using non-volatile buffer |
US20110119569A1 (en) * | 2009-11-18 | 2011-05-19 | Samsung Electronics Co., Ltd. | Apparatus and method for storing data using non-volatile buffer |
WO2011081232A1 (en) * | 2009-12-29 | 2011-07-07 | 주식회사 프롬나이 | Computing system and method for selectively implementing process persistence using nvram and volatile ram |
US20120254531A1 (en) * | 2011-03-28 | 2012-10-04 | Fujitsu Limited | Storage apparatus and storage control device |
US20130024607A1 (en) * | 2011-07-19 | 2013-01-24 | Young-Ho Park | Memory apparatus |
US8935460B2 (en) * | 2011-07-19 | 2015-01-13 | Samsung Electronics Co., Ltd. | Memory apparatus |
US9170897B2 (en) | 2012-05-29 | 2015-10-27 | SanDisk Technologies, Inc. | Apparatus, system, and method for managing solid-state storage reliability |
US9251019B2 (en) | 2012-05-29 | 2016-02-02 | SanDisk Technologies, Inc. | Apparatus, system and method for managing solid-state retirement |
US8898376B2 (en) | 2012-06-04 | 2014-11-25 | Fusion-Io, Inc. | Apparatus, system, and method for grouping data stored on an array of solid-state storage elements |
US9063845B2 (en) * | 2012-08-29 | 2015-06-23 | Buffalo Memory Co., Ltd. | Solid-state drive device |
US20140068157A1 (en) * | 2012-08-29 | 2014-03-06 | Buffalo Memory Co., Ltd. | Solid-state drive device |
US9632714B2 (en) | 2012-08-29 | 2017-04-25 | Buffalo Memory Co., Ltd. | Solid-state drive device |
US9164856B2 (en) | 2013-11-11 | 2015-10-20 | International Business Machines Corporation | Persistent messaging mechanism |
US9342419B2 (en) | 2013-11-11 | 2016-05-17 | Globalfoundries Inc. | Persistent messaging mechanism |
US20150331807A1 (en) * | 2014-12-10 | 2015-11-19 | Advanced Micro Devices, Inc. | Thin provisioning architecture for high seek-time devices |
US9734081B2 (en) * | 2014-12-10 | 2017-08-15 | Advanced Micro Devices, Inc. | Thin provisioning architecture for high seek-time devices |
WO2016122491A1 (en) * | 2015-01-28 | 2016-08-04 | Hewlett-Packard Development Company, L.P. | Page cache in a non-volatile memory |
US20180196748A1 (en) * | 2015-01-28 | 2018-07-12 | Hewlett-Packard Development Company, L.P. | Page cache in a non-volatile memory |
US10353816B2 (en) * | 2015-01-28 | 2019-07-16 | Hewlett-Packard Development Company, L.P. | Page cache in a non-volatile memory |
EP3361387A4 (en) * | 2015-10-21 | 2018-10-17 | Huawei Technologies Co., Ltd. | Data transmission method, equipment and system |
US20190220402A1 (en) * | 2018-01-18 | 2019-07-18 | EMC IP Holding Company LLC | Data recovery method, data recovery system, and computer program product |
US10860481B2 (en) * | 2018-01-18 | 2020-12-08 | EMC IP Holding Company LLC | Data recovery method, data recovery system, and computer program product |
Also Published As
Publication number | Publication date |
---|---|
KR100755700B1 (en) | 2007-09-05 |
CN1991790A (en) | 2007-07-04 |
KR20070068796A (en) | 2007-07-02 |
US7774541B2 (en) | 2010-08-10 |
CN100524249C (en) | 2009-08-05 |
JP2007179545A (en) | 2007-07-12 |
EP1804168A1 (en) | 2007-07-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7774541B2 (en) | Storage apparatus using non-volatile memory as cache and method of managing the same | |
US10649910B2 (en) | Persistent memory for key-value storage | |
US9513831B2 (en) | Method and system for atomically writing scattered information in a solid state storage device | |
US7716422B2 (en) | Storage apparatus and method for using a non-volatile cache memory organized into stationary and non-stationary circular regions | |
KR100843543B1 (en) | System comprising flash memory device and data recovery method thereof | |
US7849257B1 (en) | Method and apparatus for storing and retrieving data | |
US7761655B2 (en) | Storage system and method of preventing deterioration of write performance in storage system | |
JP5571691B2 (en) | Maintaining mapping address tables in storage | |
TWI424316B (en) | Controller, data storage device, and program product | |
US20170344287A1 (en) | Atomic write command support in a solid state drive | |
US10430285B2 (en) | Backing up metadata | |
US20150186224A1 (en) | Data storage device and flash memory control method | |
KR102033323B1 (en) | Method for storing metadata of log-structured file system for flash memory | |
EP2290544B1 (en) | A method for implementing continuous data protection utilizing allocate-on-write snapshots | |
JP2012243385A (en) | Storage device with inline address indirection metadata storage | |
JP2013061799A (en) | Memory device, control method for memory device and controller | |
EP2742428A1 (en) | Cache management including solid state device virtualization | |
EP3107005B1 (en) | Method and device for recovering checkpoint in copy on write based file system | |
US9442666B2 (en) | Optimized management of operation data in a solid-state memory | |
JP2003167690A (en) | Disk array device and data restoring method for this device | |
JP2017107318A (en) | Memory system, and information processing device and processing method | |
KR101738965B1 (en) | Apparatus and method for journaling based on garbage collection | |
CN115705152A (en) | Metadata management in non-volatile memory devices using in-memory logs | |
CN115705153A (en) | Conditional update and deferred lookup | |
US20140047161A1 (en) | System Employing MRAM and Physically Addressed Solid State Disk |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: SAMSUNG ELECTRONICS CO., LTD., KOREA, REPUBLIC OF Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:SHIN, DONG-KUN;LEE, SHEA-YUN;KIM, JANG-HWAN;AND OTHERS;REEL/FRAME:018859/0308 Effective date: 20070108 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
FPAY | Fee payment |
Year of fee payment: 4 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 8TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1552) Year of fee payment: 8 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 12TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1553); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 12 |